The AI arena is free today

Open Superagent

Gemma 3 27B vs Kimi K2 Base

Kimi K2 Base leads the LLM Stats Score 13.5 to 8.3.

Google · Moonshot AI · Updated for 2026

Which is better?

Kimi K2 Base leads the overall LLM Stats Score 13.5 to 8.3, ranking #247 overall.

In the 5 individual benchmarks reported for both models, Kimi K2 Base wins 3; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Gemma 3 27B

  • you want predictable pricing at $0.08/M input and $0.16/M output

Choose Kimi K2 Base

  • overall performance matters — it scores 13.5 and ranks #247 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 5 exact shared results
  • you want the most recent training data — it shipped Jul 2025

At a glance

The differences that matter most.

Core performance indexes
8.3
#283
13.5
#247
8.6
#274
12.6
#245
5.3
#202
10.6
#166
Cost, coverage & limits
Benchmark wins
2 of 5
3 of 5
Input price
$0.08 / M
— / M
Output price
$0.16 / M
— / M
Context window
131,072

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 3 27B
Kimi K2 Base
17.4#195
14.3#219
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

27 reported for Gemma 3 27B · 13 for Kimi K2 Base

5 shared

Gemma 3 27B outperforms in 2 benchmarks (GSM8k, MATH), while Kimi K2 Base is better at 3 benchmarks (GPQA, MMLU-Pro, SimpleQA).

Kimi K2 Base has a slight edge in benchmark performance.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

973.0B diff

Kimi K2 Base has 973.0B more parameters than Gemma 3 27B, making it 3603.7% larger.

Google
Gemma 3 27B
27.0Bparameters
Moonshot AI
Kimi K2 Base
1.0Tparameters
27.0B
Gemma 3 27B
1000.0B
Kimi K2 Base

Context Window

Maximum input and output token capacity

Only Gemma 3 27B specifies input context (131,072 tokens). Only Gemma 3 27B specifies output context (131,072 tokens).

Google
Gemma 3 27B
Input131,072 tokens
Output131,072 tokens
Moonshot AI
Kimi K2 Base
Input- tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemma 3 27B supports multimodal inputs, whereas Kimi K2 Base does not.

Gemma 3 27B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 3 27B

Text
Images
Audio
Video

Kimi K2 Base

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3 27B is licensed under Gemma, while Kimi K2 Base uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Gemma 3 27B

Gemma

Open weights

Kimi K2 Base

MIT

Open weights

Release Timeline

When each model was launched

Gemma 3 27B was released on 2025-03-12, while Kimi K2 Base was released on 2025-07-11.

Kimi K2 Base is 4 months newer than Gemma 3 27B.

Gemma 3 27B

Mar 12, 2025

1.5 years ago

Kimi K2 Base

Jul 11, 2025

1.2 years ago

4mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Gemma 3 27B and Kimi K2 Base side-by-side, then vote on the output you prefer.

Gemma 3 27B
✓ Preferred
Kimi K2 Base
Open in Playground

FAQ

Common questions about Gemma 3 27B vs Kimi K2 Base.

Which is better, Gemma 3 27B or Kimi K2 Base?

Kimi K2 Base leads the LLM Stats Score 13.5 to 8.3. Gemma 3 27B is made by Google and Kimi K2 Base is made by Moonshot AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemma 3 27B compare to Kimi K2 Base in benchmarks?

Gemma 3 27B scores GSM8k: 95.9%, IFEval: 90.4%, MATH: 89.0%, HumanEval: 87.8%, BIG-Bench Hard: 87.6%. Kimi K2 Base scores C-Eval: 92.5%, GSM8k: 92.1%, MMLU-redux-2.0: 90.2%, MMLU: 87.8%, TriviaQA: 85.1%.

What are the context window sizes for Gemma 3 27B and Kimi K2 Base?

Gemma 3 27B supports 131K tokens and Kimi K2 Base supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemma 3 27B and Kimi K2 Base?

Key differences include LLM Stats Score (8.3 vs 13.5), multimodal support (yes vs no), licensing (Gemma vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 3 27B and Kimi K2 Base?

Gemma 3 27B is developed by Google and Kimi K2 Base is developed by Moonshot AI.